Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to historical or archaeological locations and artifacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     çģ
    -0.06
    Tower
    -0.06
     Tower
    -0.06
     gren
    -0.05
    asis
    -0.05
    оÑĤÑĮ
    -0.05
     dyst
    -0.05
    ãĥ¡ãĥ³ãĥĪ
    -0.05
     Landing
    -0.05
     Pond
    -0.05
    POSITIVE LOGITS
     cave
    0.23
     caves
    0.21
     Cave
    0.18
     rock
    0.14
     cav
    0.14
     cavern
    0.14
    rock
    0.13
     cavity
    0.13
    -rock
    0.12
     اÙĦÙĥÙĩ
    0.12
    Act Density 0.033%

    No Known Activations